Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/stumason/coolify-mcp/claude-mdgit clone --depth 1 https://github.com/StuMason/coolify-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/stumason/coolify-mcp/claude-md)<a href="https://agentmods.dev/instructions/stumason/coolify-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/stumason/coolify-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03536 | $0.03536 |
| Opus 5 | $0.01768 | $0.01768 |
| Sonnet 5 | $0.00707 | $0.00707 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade A, and why
coolify-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MCP (Model Context Protocol) server for Coolify that provides 44 token-optimized tools for AI assistants to manage infrastructure through natural language. Tools cover servers, projects, environments, applications, databases, services, deployments, private keys, teams, cloud tokens, documentation search, smart diagnostics, and batch operations. v2.0.0 reduced token usage by 85% (from ~43,000 to ~6,600 tokens) by consolidating related operations into single tools with action parameters.
Commands
npm install # Install dependencies
npm run build # Build TypeScript to dist/
npm test # Run all tests
npm run lint # Run ESLint
npm run format # Run Prettier
# Run locally
COOLIFY_BASE_URL="https://your-coolify.com" COOLIFY_ACCESS_TOKEN="token" node dist/index.js
Evals & red teaming (evals/)
Self-contained package (own package.json/toolchain, like site/) that treats
tool descriptions as prompts and measures them. If you edit a tool's name,
description, schema or annotation, evals tool-contract snapshots will fail
until you review and npm run snapshots:update. Layers: (1) contract snapshots,
(2) tool-selection evals, (3) prompt-injection regression, (4) promptfoo red
team. All runs use a fixture backend that refuses to start if COOLIFY_URL
looks real. See evals/README.md; findings in evals/FINDINGS.md — note #4
(secret-exfiltration-via-log-injection on weak models, fixed: asUntrustedLogs
frames every model-facing log surface — logs, application_logs, diagnose_app,
diagnose_server validation output, and all deployment/deploy build output
(logs_tail, get, list_for_app) — as untrusted data, with a per-call nonce so
the boundary can't be forged;
5/5→0/5 leaks on Gemini) and
#5 (frontier models act on vague requests, validating the elicitation guard).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 187 lines · 3,536 tokens per session scan A 9b43a24a67f0
coolify-mcp CLAUDE.md is an instructions file published in the GitHub repository StuMason/coolify-mcp (578 stars, last pushed yesterday), licensed MIT. It adds 3,536 tokens to every session, about $0.0177 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
coolify-mcp CLAUDE.md
Claude Code instructions for jurislm/coolify-mcp, covering claude.md, project overview, commands, run locally and architecture.
coolify-mcp copilot-instructions.md
Copilot instructions for jurislm/coolify-mcp, covering copilot instructions for coolify-mcp, project overview, git workflow, version numbers and build & test.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.